Senior Research Engineer, Audio and Speech

Decagon is hiring a Senior Research Engineer focused on Audio and Speech to build models and agent harnesses for real-time voice agents, advancing multimodal and full-duplex systems from research through production. The role focuses on improving speech capabilities, evaluating production performance, and optimizing inference for responsiveness, stability, and scale.

Responsibilities:

• Design and build next-generation agent harnesses optimized for streaming speech, turn-taking, interruptions, overlapping speech, and continuous interaction
• Research and train multimodal and full-duplex models that jointly understand audio, reason, and generate speech
• Improve speech recognition, voice activity detection, endpointing, and speech generation across diverse speakers, environments, domains, and languages
• Build evaluations and use production calls to ship measurable improvements in accuracy, latency, naturalness, and task outcomes
• Optimize end-to-end inference for responsiveness, throughput, stability, and cost, partnering with Voice Platform and Infrastructure teams to deploy at scale